Voice activity detection with quasi-quadrature filters and GMM decomposition for speech and noise
Sign Up to like & getrecommendations! Published in 2020 at "Applied Acoustics"
DOI: 10.1016/j.apacoust.2020.107344
Abstract: Abstract One of basic algorithms employed in technologies such as automatic speech recognition (ASR) systems is voice activity detection (VAD). Speech contains many pauses, whose interpretation might lead to recognition errors. Scientific literature provides numerous… read more here.
Keywords: voice activity; speech; detection; activity detection ... See more keywords
Analysis of derivative of instantaneous frequency and its application to voice activity detection
Sign Up to like & getrecommendations! Published in 2021 at "Applied Acoustics"
DOI: 10.1016/j.apacoust.2021.108116
Abstract: Abstract Recently, the use of speech processing in a time–frequency domain that handles the phase spectrum in addition to the amplitude one has been increasing because many studies have revealed the importance of phase. Inspired… read more here.
Keywords: frequency; voice activity; phase; derivative instantaneous ... See more keywords
Voice Activity Detection Optimized by Adaptive Attention Span Transformer
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3262518
Abstract: Voice Activity Detection (VAD) is a widely used technique for separating vocal regions from audio signals, with applications in voice language coding, noise reduction, and other domains. While various strategies have been proposed to improve… read more here.
Keywords: voice activity; activity detection; vad; voice ... See more keywords
A Low-Power Speech Recognizer and Voice Activity Detector Using Deep Neural Networks
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Journal of Solid-State Circuits"
DOI: 10.1109/jssc.2017.2752838
Abstract: This paper describes digital circuit architectures for automatic speech recognition (ASR) and voice activity detection (VAD) with improved accuracy, programmability, and scalability. Our ASR architecture is designed to minimize off-chip memory bandwidth, which is the… read more here.
Keywords: deep neural; neural networks; voice activity; power ... See more keywords
A 108-nW 0.8-mm2 Analog Voice Activity Detector Featuring a Time-Domain CNN With Sparsity-Aware Computation and Sparsified Quantization in 28-nm CMOS
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Journal of Solid-State Circuits"
DOI: 10.1109/jssc.2022.3191008
Abstract: This article reports a passive analog feature extractor for realizing an area-and-power-efficient voice activity detector (VAD) for voice-control edge devices. It features a switched-capacitor circuit as the time-domain convolutional neural network (TD-CNN) that extracts the… read more here.
Keywords: voice activity; sparsity aware; activity detector; voice ... See more keywords